Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    github

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     counterparts
    -0.07
     Luis
    -0.06
     ensuite
    -0.06
    nict
    -0.06
     french
    -0.06
     alte
    -0.06
     Visualization
    -0.06
    ois
    -0.06
    ρθρο
    -0.06
    Weights
    -0.06
    POSITIVE LOGITS
     '''
↵
    0.07
    github
    0.07
     Zot
    0.07
     */;↵
    0.06
    aws
    0.06
    (substr
    0.06
    .Margin
    0.06
    划
    0.06
     SIDE
    0.06
    OfDay
    0.06
    Act Density 0.003%

    No Known Activations